ChromaDB doesnt save etc

# import
from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
from llama_index.vector_stores import ChromaVectorStore
from llama_index.storage.storage_context import StorageContext
from llama_index.embeddings import HuggingFaceEmbedding
from IPython.display import Markdown, display
import chromadb
from llama_index.llms import LlamaCPP
print("Calling LLM")
llm = LlamaCPP(
    # You can pass in the URL to a GGML model to download it automatically
    # optionally, you can set the path to a pre-downloaded model instead of model_url
    model_path="./models/em_german_13b_v01.Q8_0.gguf",
    temperature=0.1,
    max_new_tokens=4048,
    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
    context_window=8128,
    # kwargs to pass to __call__()
    generate_kwargs={},
    # kwargs to pass to __init__()
    # set to at least 1 to use GPU
    # model_kwargs={"n_gpu_layers": 1},
    # transform inputs into Llama2 format
    # messages_to_prompt=messages_to_prompt,
    # completion_to_prompt=completion_to_prompt,
    verbose=True,
    
)
print("Called LLM")
print("Making PersistentClient")

db = chromadb.PersistentClient(path="./chroma_db")
print("Made PersistentClient")
print("Making client")
print("Made client")
print("Creating collection")
chroma_collection = db.get_or_create_collection("sampledata")#
print(chroma_collection)
print("Created collection")
# define embedding function
print("Creating embedding model")
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5")
print("Created embedding model")
# load documents
print("Loading documents")
documents = SimpleDirectoryReader("./sample_data").load_data()
print("Loaded documents")

# set up ChromaVectorStore and load in data
print("Creating vector store")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
print("Created vector store")
print("Loading data into vector store")
storage_context = StorageContext.from_defaults(vector_store=vector_store)
print("Loaded data into vector store")
print("Making ServiceContext")
service_context = ServiceContext.from_defaults(llm=llm, embed_model="local:BAAI/bge-base-en-v1.5")

print("Made ServiceContext")
print("Making index")
index = VectorStoreIndex.from_documents(documents, service_context=service_context)

print("Made index")

# Query Data
print("Querying data")
query_engine = index.as_query_engine()
print("Queried data")
print("Getting response")
response = query_engine.query("Was ist der Prozess \"Düngen\"? Bitte nutze Leerzeichen zwischen den Wörtern. Und nutze Satzzeichen.")
print("Got response")
print("Printing response")
print(response)

print("Printed response")
print("Printing response source nodes")
print(response.source_nodes)
print("Printed response source nodes")

import chromadb
from llama_index import VectorStoreIndex
from llama_index.vector_stores import ChromaVectorStore
from llama_index.storage.storage_context import StorageContext
from llama_index.llms import LlamaCPP
from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext

# initialize client
db = chromadb.PersistentClient(path="./chroma_db")
llm = LlamaCPP(
    # You can pass in the URL to a GGML model to download it automatically
    # optionally, you can set the path to a pre-downloaded model instead of model_url
    model_path="./models/em_german_13b_v01.Q8_0.gguf",
    temperature=0.1,
    max_new_tokens=4048,
    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
    context_window=8128,
    # kwargs to pass to __call__()
    generate_kwargs={},
    # kwargs to pass to __init__()
    # set to at least 1 to use GPU
    # model_kwargs={"n_gpu_layers": 1},
    # transform inputs into Llama2 format
    # messages_to_prompt=messages_to_prompt,
    # completion_to_prompt=completion_to_prompt,
    verbose=True,
    
)
# get collection
chroma_collection = db.get_or_create_collection("sampledata")
print(chroma_collection)
# assign chroma as the vector_store to the context
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
service_context = ServiceContext.from_defaults(llm=llm, embed_model="local:BAAI/bge-base-en-v1.5")

# load your index from stored vectors
index = VectorStoreIndex.from_vector_store(
    vector_store, storage_context=storage_context, service_context=service_context
)


# create a query engine
query_engine = index.as_query_engine()
response = query_engine.query("Was ist der Prozess \"Düngen\"? Bitte nutze Leerzeichen zwischen den Wörtern. Und nutze Satzzeichen.")
print(response)
print(response.source_nodes)

chat_engine = index.as_chat_engine()

TypeError: Object of type ChatMessage is not JSON serializable

response_data = {
        "message": message.json(),
        "answer": responsestuff.response,
        "timeinfo": time,
        #"sourcetext": responsestuff.get_formatted_sources()
        "chat_history": [x.json() for x in custom_chat_history],
    }

from llama_index.llms import ChatMessage

chat_history = [ChatMessage.parse_raw(x) for x in json_chat_history]

response_data = {
        "message": message,
        "answer": responsestuff.response,
        "timeinfo": time,
        #"sourcetext": responsestuff.get_formatted_sources()
        "chat_history": [x.json() for x in custom_chat_history],
    }

if responsestuff.response == "":
        response_data = {
            "message": message,
            "answer": "Ich weiß nicht, es tut mir leid.",
            "timeinfo": time,
            # "sourcetext": responsestuff.get_formatted_sources()
            "chat_history": custom_chat_history,
        }
        responsestuff.response = "Ich weiß nicht, es tut mir leid."